Skip to content
Open access

Multi-Scale Attention-Enhanced BiLSTM Network for EEG Emotion Recognition

2026 · IEEE Access · Vol 14, pp. 172548-172562 · 0 citations · 37 references

TL;DR

An EEG-specific lightweight architecture for affective computing titled multi-scale Bidirectional Long Short-Term Memory with Attention (MS-BiLSTM-Attention) is introduced, which combines a multi-scale convolutional neural network, a Bidirectional Long Short-Term Memory, and a channel–spatial attention mechanism to jointly extracts and integrates spectral, topology-indexed, and channel-wise information from EEG signals.

Abstract

Over the last decade, significant progress has been made in detecting human emotions via electroencephalographic (EEG) recordings. Nevertheless, contemporary EEG-driven affect recognition techniques continue to encounter multiple hurdles, including insufficient feature extraction capability, inadequate modeling of local patterns, low feature extraction efficiency, high model complexity, and difficulty in practical deployment. To address these issues, we introduce an EEG-specific lightweight architecture for affective computing titled multi-scale Bidirectional Long Short-Term Memory with Attention (MS-BiLSTM-Attention). This model uses DE features, which are embedded into the EEG electrode topology to preserve spatial information. By combining a multi-scale convolutional neural network (CNN), a Bidirectional Long Short-Term Memory (BiLSTM), and a channel–spatial attention mechanism, the proposed framework jointly extracts and integrates spectral, topology-indexed, and channel-wise information from EEG signals. The main architectural contributions of this work are as follows: (i) dividing the EEG signal into 0.5-second time windows, extracting DE features across multiple frequency bands, and mapping each segment onto the EEG electrode topology to construct segment-level topology representations for subsequent multi-scale feature encoding; (ii) developing an EEG-specific Parallel Multi-scale Spectral–Topological Bidirectional Encoder for multi-scale spectral and topology-indexed feature extraction; (iii) proposing a lightweight Convolutional Additive Attention Module (CAAM) with a Convolutional Additive Token Mixer (CATM) to adaptively enhance channel-wise and spatial feature representations with low computational overhead. Independent experiments were conducted on the DEAP and MAHNOB-HCI datasets under both subject-dependent and subject-independent protocols. Across DEAP and MAHNOB-HCI, the model achieved subject-dependent arousal and valence accuracies above 92%, while using 25.52 K parameters and 0.6 MFLOPs per sample, establishing a favorable accuracy–complexity profile for EEG affective computing.

Read PDF

Similar papers

Review Open access Oct 2026

A Survey on Attention-Based Deep Learning Methods for EEG Emotion Recognition

Future research is expected to develop more efficient and interpretable attention mechanisms while exploring larger datasets and multimodal learning frameworks, which may further improve the robustness and practical application of EEG emotion recognition systems.

Zhi-Xuan Qi · 0 citations
Open access Oct 2026

FPGLNet: A Lightweight Frequency Prior-Gated Network for EEG Emotion Recognition

Although deep learning-based electroencephalography (EEG) emotion recognition methods have achieved promising performance, they generally depend on complex network architectures and high computational costs, which limits their deployment in resource-constrained scenarios. Meanwhile, existing approaches mainly focus on...

Yue Yuan, Ying-Zhou Bi, Shan-Rui Liu et al. · 0 citations
Open access Oct 2026

Balancing Local and Global Dependencies in EEG Emotion Recognition via Multi-Scale Hybrid Attention

Electroencephalography (EEG)-based emotion recognition remains challenging due to the low signal-to-noise ratio, non-stationarity, strong inter-subject variability, and the distribution of affect-related information across multiple temporal resolutions. Although recent deep architectures have increasingly combined mult...

Yi-Ren Ding, Yang-Fan Wang, Rui Wang et al. · 0 citations
Oct 2026

Multi-Domain Representation Learning For Enhanced EEG-Based Emotion Recognition

A dual-branch feature fusion architecture that integrates complementary EEG features that outperforms existing methods in emotion classification and enables effective exploitation of complementary EEG information is proposed.

Yuan-Yuan Gao, Shu-Hui Liu, Ji-Ye Zhan et al. · 0 citations
Open access Oct 2026

Spatio temporal graph attention transformer for EEG based emotion recognition using DEAP and SEED datasets

A Spatio-Temporal Graph Attention Transformer (ST-GAT) framework that jointly learns spatial and temporal representations from multi-channel EEG signals for EEG-based emotion recognition across multiple benchmark datasets is proposed.

Sonu Kumar Jha, Indrajeet Kumar, M. Kumar et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.